Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Evolvlabsai/Exolvra-GenesisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/evolvlabsai/exolvra-genesis/interview)<a href="https://agentmods.dev/commands/evolvlabsai/exolvra-genesis/interview"><img src="https://agentmods.dev/badge/commands/evolvlabsai/exolvra-genesis/interview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/evolvlabsai/exolvra-genesis/interview"><img src="https://agentmods.dev/badge/commands/evolvlabsai/exolvra-genesis/interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00854 |
| Opus 5.5 | $0.00016 | $0.00342 |
| Sonnet 5.5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running an Exolvra Genesis interview. The output is two files the user owns:
a spec that /exolvra-genesis:run can execute directly, and a single-file
interactive mockup that doubles as a visual bar candidate for the run. This
command is a conversation, not a build — you write both files yourself; no
subagents.
$ARGUMENTS
When a proposed specification involves claims, locks, recovery, concurrent actors, or attackers, include protocol modeling in its acceptance criteria: a TLA+ model, an exhaustive TypeScript explorer run under the existing Node test suite, the same named invariants in both, declared state-space bounds, and a counterexample from a deliberately broken variant. A model without its exhaustive check is unfinished. No Java or additional runtime dependency is required.
Mode
If the input is a path to an existing spec, this is a modification pass: read the spec (and its mockup, if referenced), summarize what exists in three sentences, and ask what should change. Otherwise start fresh, seeded by whatever idea the input contains.
The interview
One question at a time, never two in one message. Short questions, with concrete options when they help. Adapt — skip what's already answered, dig where answers are vague. Cover, in whatever order the conversation makes natural:
- The thing — what's being built, for whom, and the one job it must do.
- Tech stack — languages, frameworks, runtime, storage, deploy target. If the user doesn't care, propose a sensible default and confirm it.
- Must-haves — the requirements. Push each until it's checkable.
- Hard gates — constraints that make the run an automatic LOSS if violated: stack, performance, size, licensing, accessibility.
- Non-goals — what's explicitly out, so builders don't wander.
- The bar — what existing thing should this be indistinguishable from, or measurably better than? Collect links, files, numbers.
Stop interviewing when new answers stop changing the spec — usually six to ten questions.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +7 lines 560d80a0f653
- 1mo ago First seen · 76 lines · 41 tokens per session scan A 9fc7b46922e3
interview is a command published in the GitHub repository Evolvlabsai/Exolvra-Genesis (1 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 854 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
update
Update Megazord to the latest version.
debug
Systematic four-phase debugging (reproduce, isolate, root-cause, fix).
discuss
Socratic brainstorming to explore approaches before implementation.
go
Execute the current phase plan with subagent delegation.
help
Show all available Megazord skills with descriptions and usage examples.
init
Initialize a Megazord project with configuration and planning structure.